• CN:11-2187/TH
  • ISSN:0577-6686

›› 2008, Vol. 44 ›› Issue (6): 66-71.

• 论文 • 上一篇    下一篇

基于支持矢量机的小波域超声信号消噪技术

杨克己;乔华伟   

  1. 浙江大学现代制造工程研究所
  • 发布日期:2008-06-15

Denoising Techniques for Ultrasonic Signals in Wavelet Domain Based on Support Vector Machine

YANG Keji;QIAO Huawei   

  1. Institute of Modern Manufacture Engineering, Zhejiang University
  • Published:2008-06-15

摘要: 为了提高超声无损检测与无损评价基础数据的信噪比,提出一种基于支持矢量机模式识别理论的小波域超声信号消噪技术。该技术在研究材料内部散射体引起的结构噪声产生机理,以及分析传统裂谱分析算法局限性的基础上,利用小波变换方法将原始超声检测信号分解到小波空间,并通过采用以高斯函数为核函数的支持矢量机所构成的信噪分离器对信号和噪声进行识别、分离来消除噪声,得到高信噪比的超声回波信号。试验结果表明,与传统裂谱分析算法相比,该技术提高了消噪性能的稳定性,增强了湮没材料内部各种散射体散射中的缺陷回波信号能力。

关键词: 超声无损检测, 小波变换, 信噪比, 支持矢量机

Abstract: In order to enhance the signal to noise ratio (SNR) of fundamental ultrasonic echo signals for ultrasonic nondestructive testing (UNDT) and ultrasonic nondestructive evaluation (UNDE), an improved technique to suppress structural noises of ultrasonic signals on the basis of pattern recognition theory of support vector machine is presented. After the formation mechanism of structural noises is studied and the shortcomings of classical split spectrum processing (SSP) algorithm are analyzed, the fundamental ultrasonic signals are decomposed into wavelet domain by discrete wavelet transform. A signal and noise separator based on support vector machine(SVM) of which the kernel function is Gauss function is used to distinguish the target signals from the noises in wavelet domain, and the target signals are reconstructed to realize the aim of enhancing SNR by removing noises. The experimental results indicate that the presented technique has high performance reliability and can improve the SNR enhancing ability for ultrasonic target echo signals contaminated by structural noises compared with the classical SSP algorithm.

Key words: Signal to noise ratio (SNR), Support vector machine (SVM), Ultrasonic nondestructive testing(UNDT), Wavelet transform

中图分类号: